Marginal rates of substitution in the presence of non-discretionary factors: A data envelopment analysis approach

Marginal rates of substitution are important quantities for analysts and managers. The current paper focuses on estimating these quantities in the presence of nondiscretionary factors in performance measurement of a group of production units. We propose a DEA framework to verify how an efficient unit would perform in two different environments and find out how the efficiency scores depends on locating the units in a more or less favorable environment. An empirical study in banking is then used to illustrate the applicability of the proposed approach.